L4 Statistical techniques and sampling designs

Question 1

Descriptive statistics

Answer 1

Methods of summarizing the data in an informative way

• central tendency: mean, median, mode
• dispersion: range, stdev, variance, interquartile range

Question 2

Inferential statistics

Answer 2

Methods to draw conclusions (or to make inferences, test hypotheses)
• Mean difference test
• Chi-square test
• Analysis of variance (ANOVA)
• Regression analysis
• Logit analysis

Question 3

Four types of scales

Answer 3

• Nominal (qualitative)
• Ordinal (qualitative)
• Interval (quantitative)
• ratio (quantitative)

Question 4

Nominal scale

Answer 4

allows classifying data into groups/categories

e.g. gender

Question 5

Ordinal scale

Answer 5

rank orders in a meaningful way

e.g. education level

Question 6

Interval scale

Answer 6

Meaningful differences between values, but no natural zero point –> zero means something (0 degrees)

Question 7

Ratio scale

Answer 7

Meaningful differences and ratios between values due to a natural zero point –> zero is actually nothing (0 dollar is no money)

Question 8

Choosing between inferential statistics:

IV=nominal/ordinal DV=nominal/ordinal

Answer 8

Chi-square test

Question 9

Choosing between inferential statistics:

IV=nominal/ordinal DV=interval/ratio

Answer 9

T-test, Anova

Question 10

Choosing between inferential statistics:

IV=interval/ratio DV=nominal/ordinal

Answer 10

logit analysis

Question 11

Choosing between inferential statistics:

IV=interval/ratio DV=interval/ratio

Answer 11

regression analysis

Question 12

When to perform T-Test vs Anova

Answer 12

T-Test –> compare two means (two levels of IV)

Anova –> compare more than two levels

Question 13

Rating scales

Answer 13

• Likert scale: strongly agree/disagree
• Semantic differential: Cold warm

TREATED AS INTERVAL/RATIO so that you can use regression

Question 14

What is a population?

Answer 14

Entire group of people, firms, events, or things of interest for which you would like to make inferences

Question 15

What is a sample?

Answer 15

A subset of the population of interest

Question 16

What is a subject?

Answer 16

Single member

Question 17

What is low representativeness?

Answer 17

= properties of the population are over- or underrepresented in the sample
= high sampling error

Question 18

The sampling process

Answer 18

1. define population
2. determine sampling frame
3. determine sampling design
4. determine sample size

Question 19

1. define population

Answer 19

e.g. students TISEM, dutch organ donors

Question 20

2. determine sampling frame

Answer 20

“Physical” representation of the target population

- where you can reach out to e.g. Donorregister

Question 21

coverage error

Answer 21

sampling frame ≠ population
• Under-coverage: true population members are excluded
• Miss-coverage: non-population members are included

Question 22

solutions to coverage error

Answer 22

• If small, recognize but ignore

* If large, redefine the population in terms of the sampling frame

Question 23

3. determine sampling design

Answer 23

probability vs non-probability sampling

Question 24

Probability sampling

Answer 24

Each element of the population has a known chance
of being selected as a subject

–>Results generalizable to population
BUT more time and resource intensive

Question 25

Nonprobability sampling

Answer 25

The elements of the population do not have a known chance of being selected as a subject --> less time and resource intensive BUT results not generalizable to population

Question 26

Probability sampling techniques

Answer 26

- Simple random sampling (SRS) - Systematic sampling - Stratified sampling - Cluster sampling

Question 27

Simple random sampling (SRS)

Answer 27

Each population element has an equal chance of being chosen e.g. out of a hat --> Highest generalizability BUT costly?

Question 28

Systematic sampling

Answer 28

Select random starting point and then pick every nth element --> simplicity BUT low generalizability if there happens to be a systematic difference between every nth observation

Question 29

Stratified sampling

Answer 29

Divide the population in meaningful (homogenous) groups, then apply SRS within each group e.g. level of income --> All groups are adequately sampled, allowing for group comparisons BUT more time consuming and Requires homogenous subgroups

Question 30

Cluster sampling

Answer 30

Divide the population in heterogeneous groups, randomly select a number of groups and select each member within these groups e.g. geographic clusters (areas) --> Geographic clusters BUT Subsets of naturally occurring clusters are typically more homogeneous than heterogeneous

Question 31

Nonprobability sampling

Answer 31

- Convenience sampling - Quota sampling - Judgment sampling - Snowball sampling

Question 32

Convenience sampling

Answer 32

Select subjects who are conveniently available e.g. random on the street --> Convenient (inexpensive and fast) BUT lower generalizability

Question 33

Quota sampling

Answer 33

Fix quota for each subgroup (percentage in population) --> When minority participation is critical BUT lower generalizability

Question 34

Judgment sampling

Answer 34

Select subjects based on their knowledge/professional judgment e.g. experts --> Convenient (inexpensive and fast) when a limited # of people has the info you need BUT Lower generalizability

Question 35

Snowball sampling

Answer 35

“Do you know people who...” e.g. people with rare disease --> For rare characteristics (“experts”) BUT first participants strongly influence the sample

Question 36

Rules of thumb for sample size

Answer 36

• Sample size ≥ 75, < 500 • Multivariate research: ≥ 10 x parameters to be estimated • Subsamples (e.g., male/female): ≥ 30 per subsample